nle-video-editor-pro
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions and examples for using shell-based tools including
ffmpeg,ffprobe, andhyperframesto perform media processing, audio extraction, and transcription tasks. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing external media files and generating transcriptions, which creates a potential surface for indirect injection if malicious instructions are embedded in the source media or metadata.
- Ingestion points: Untrusted media files (
input.mp4) are processed to extract audio and generate transcriptions (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore content originating from the transcription process.
- Capability inventory: The skill uses shell execution capabilities via media processing and transcription tools.
- Sanitization: No explicit sanitization or validation of the input media or generated transcription text is mentioned.
Audit Metadata